datamodules.RotNet.utils package
Submodules
datamodules.RotNet.utils.image_analytics module
- get_analytics_data(input_path: Path, data_folder_name: str, get_gt_data_paths_func: callable, inmem=False, workers=8) Dict[str, Any][source]
Get analytics data from json file or compute it and save it to json file.
- Parameters:
input_path (Path) – path to the training set
data_folder_name (str) – name of the folder containing the data
get_gt_data_paths_func (callable) – function to get the paths to the gt data
inmem (bool) – Should the data be loaded fully into memory
workers (int) – Number of workers to be used for calculating the mean and std
- Returns:
analytics data
- Return type:
Dict[str, Any]
datamodules.RotNet.utils.misc module
- validate_path_for_self_supervised(data_dir: str, data_folder_name: str) Path[source]
Validates the path for the self-supervised learning task. The path should contain a train/val/test folder and each of them a folder with the name of the data_folder_name.
- Parameters:
data_dir (str) – Root dir of the dataset (folder containing the train/val/test folder)
data_folder_name (str) – Name of the folder containing the data
- Raises:
PathNone – If data_dir is None
PathNotDir – If data_dir is not a directory
PathMissingSplitDir – If data_dir does not contain train/val/test
PathMissingDirinSplitDir – If train/val/test does not contain data_folder_name
- Returns:
Path to the root dir of the dataset
- Return type:
Path